sinergym.utils.wrappers.NormalizeAction
- class sinergym.utils.wrappers.NormalizeAction(env: EplusEnv, normalize_range: Tuple[float, float] = (-1.0, 1.0))
Wrapper to normalize action space.
- __init__(env: EplusEnv, normalize_range: Tuple[float, float] = (-1.0, 1.0))
Wrapper to normalize action space in default continuous environment (not to combine with discrete environments). The action will be parsed to real action space before to send to the simulator (very useful ion DRL algorithms)
- Parameters:
env (EplusEnv) – Original environment.
normalize_range (Tuple[float,float]) – Range to normalize action variable values. Defaults to values between [-1.0,1.0].
Methods
__init__
(env[, normalize_range])Wrapper to normalize action space in default continuous environment (not to combine with discrete environments).
action
(action)Returns a modified action before
env.step()
is called.class_name
()Returns the class name of the wrapper.
close
()Closes the wrapper and
env
.get_wrapper_attr
(name)Gets an attribute from the wrapper and lower environments if name doesn't exist in this object.
render
()Uses the
render()
of theenv
that can be overwritten to change the returned data.reset
(*[, seed, options])Uses the
reset()
of theenv
that can be overwritten to change the returned data.reverting_action
(action)This method maps a normalized action in a real action space.
step
(action)Runs the
env
env.step()
using the modifiedaction
fromself.action()
.wrapper_spec
(**kwargs)Generates a WrapperSpec for the wrappers.
Attributes
action_space
Return the
Env
action_space
unless overwritten then the wrapperaction_space
is used.metadata
Returns the
Env
metadata
.np_random
Returns the
Env
np_random
attribute.observation_space
Return the
Env
observation_space
unless overwritten then the wrapperobservation_space
is used.render_mode
Returns the
Env
render_mode
.reward_range
Return the
Env
reward_range
unless overwritten then the wrapperreward_range
is used.spec
Returns the
Env
spec
attribute with the WrapperSpec if the wrapper inherits from EzPickle.unwrapped
Returns the base environment of the wrapper.
- action(action: Any)
Returns a modified action before
env.step()
is called.- Parameters:
action – The original
step()
actions- Returns:
The modified actions
- logger = <Logger WRAPPER NormalizeAction (INFO)>
- reverting_action(action: Any) List[float]
This method maps a normalized action in a real action space.
- Parameters:
action (Any) – Normalize action received in environment
- Returns:
Action transformed in simulator real action space.
- Return type:
List[float]